Evolutionary Computation
Evolutionary computation (EC) is a powerful optimization and learning paradigm inspired by natural selection, aiming to find optimal solutions to complex problems by iteratively improving a population of candidate solutions. Current research emphasizes the integration of EC with large language models (LLMs) for automated hyperparameter tuning and heuristic design, as well as the development of novel, simpler algorithms like BMR and BWR for tackling real-world constrained and unconstrained optimization problems. The impact of EC is significant, extending to diverse fields such as robotic design, machine learning model optimization, and the design of efficient algorithms for resource-constrained problems, demonstrating its broad applicability and potential for solving challenging real-world optimization tasks.
Papers
Computing High-Quality Solutions for the Patient Admission Scheduling Problem using Evolutionary Diversity Optimisation
Adel Nikfarjam, Amirhossein Moosavi, Aneta Neumann, Frank Neumann
Co-Evolutionary Diversity Optimisation for the Traveling Thief Problem
Adel Nikfarjam, Aneta Neumann, Jakob Bossek, Frank Neumann